with one click
research-goal
// Goal-driven finance research workflow: attach a research-only objective, track criteria, and add evidence while avoiding live trading execution.
// Goal-driven finance research workflow: attach a research-only objective, track criteria, and add evidence while avoiding live trading execution.
| name | research-goal |
| description | Goal-driven finance research workflow: attach a research-only objective, track criteria, and add evidence while avoiding live trading execution. |
Use this skill when a user asks for a multi-step finance research task, comparison, audit, thesis review, or "keep working until the answer is supported." The goal runtime is for research only. Never use it to place, submit, or execute trades.
Start a goal when the task has any of these traits:
Do not start a goal for a tiny one-shot answer unless the user explicitly asks.
start_research_goal with a concise research-only objective.get_research_goal.add_goal_evidence.criterion_id or criterion_index.update_research_goal_status.Use this shape when the user did not provide criteria:
run_id, artifact_path, source_provider, source_type, symbol_universe, benchmark, and data_as_of when known.tool_call_id is traceability only. Completion needs verified evidence from an existing run_id or an allowed artifact_path with a matching sha256 hash.update_research_goal_status(status="complete") only after every required criterion has an audit row.evidence_ids.status="blocked" or status="insufficient_evidence" when evidence is missing, stale, contradictory, or not verifiable.status="cancelled" only when the user explicitly asks to end or discard the goal.Tell the user what the goal is tracking only when it helps. Do not flood the answer with ledger details. Lead with the research conclusion, then mention which criteria remain unresolved.
Professional finance research toolkit — backtesting (7 engines + benchmark comparison panel), factor analysis, Alpha Zoo (452 pre-built alphas across qlib158/alpha101/gtja191/academic), options pricing, 75 finance skills, 29 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest → render) across 7 data sources (tushare, yfinance, okx, akshare, mootdx, ccxt, futu).
Mootdx A-share market data via TCP-direct 通达信 servers. Free, no API key, no IP rate limits. Use as the stable A-share OHLCV fallback when akshare's East Money scrape is throttled.
Browse and bench the bundled alpha zoos — prebuilt cross-sectional factor libraries (Kakushadze 101, GTJA 191, Qlib 158, Fama-French / Carhart). Use when the user asks "which alphas exist", wants metadata on a named alpha, or wants to run IC/IR on a whole zoo over a universe.
Factor research framework with IC/IR analysis, quantile backtesting, and factor combination. Suitable for cross-sectional factor evaluation across multiple instruments.
Multi-factor cross-sectional stock ranking. Combines factor standardization, equal-weight or IC-weighted scoring, and TopN portfolio construction. Suitable for multi-instrument portfolio strategies.
Read web pages, articles, and document links by converting URLs into Markdown text. Use the `read_url` tool directly, without bash. Sends the full URL to the third-party Jina Reader (r.jina.ai).